Action recognition based on spatio-temporal information and nonnegative component representation

DOI10.3969/J.ISSN.1001-0505.2016.04.001MaRDI QIDQ2987069zbMATH OpenFDO

Authors Jianhong Wang, Xu Zhang, Pinzheng Zhang, Longyu Jiang, Limin Luo

Publication date 17 May 2017

Full work available at URL https://doi.org/10.3969/J.ISSN.1001-0505.2016.04.001

zbMATH Keywords

action recognitionbag of visual wordsnonnegative component representationspatio-temporal Fisher vector

Mathematics Subject Classification ID

Pattern recognition, speech recognition (68T10) Machine vision and scene understanding (68T45)

Recommendations

• Space-time tree ensemble for action recognition and localization
• A new spatial-temporal histograms of gradients descriptor and HOD-VLAD encoding for human action recognition
• Structural iMoSIFT for human action recognition
• Local spatio-temporal representation using the 3D shearlet transform
• Nonnegative tensor-based linear dynamical systems for recognizing human action from 3D skeletons

Cited in

(8)

• Space-time tree ensemble for action recognition and localization
• Nonnegative tensor-based linear dynamical systems for recognizing human action from 3D skeletons
• Structural iMoSIFT for human action recognition
• Mining layered grammar rules for action recognition
• Action recognition with hierarchical convolutional neural networks features and bi-directional long short-term memory model
• Local spatio-temporal representation using the 3D shearlet transform
• A new spatial-temporal histograms of gradients descriptor and HOD-VLAD encoding for human action recognition
• Multi-layer representation for cross-view action recognition

This page was built for publication: Action recognition based on spatio-temporal information and nonnegative component representation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2987069)